Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    come up with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Weird
    0.86
    sette
    0.85
    tipo
    0.84
     excelencia
    0.84
    twisted
    0.83
    mandatory
    0.81
    suite
    0.81
     compone
    0.80
     বিষয়ে
    0.79
     dolazi
    0.77
    POSITIVE LOGITS
    меры
    0.67
     kung
    0.67
     решений
    0.67
    ált
    0.67
     conco
    0.66
    অর্
    0.66
    ôm
    0.64
     நிர்
    0.64
     decide
    0.63
    拠
    0.63
    Act Density 0.026%

    No Known Activations